• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ´ëÈ­ ¸»¹¶Ä¡ ±¸ÃàÀ» À§ÇÑ ¹ÝÀÚµ¿ ÀǹÌÇ¥Áö ÅÂ±ë ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) A Semi-Automatic Semantic Mark Tagging System for Building Dialogue Corpus
ÀúÀÚ(Author) ¹ÚÁØÇõ   À̼º¿í   ÀÓÀ±¼·   ÃÖÁ¾¼®   Junhyeok Park   Songwook Lee   Yoonseob Lim   Jongsuk Choi   ¹ÚÁØÇõ   À̼º¿í   ÀÓÀ±¼·   ÃÖÁ¾¼®   Junhyeok Park   Songwook Lee   Yoonseob Lim   Jongsuk Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 08 NO. 05 PP. 0213 ~ 0222 (2019. 05)
Çѱ۳»¿ë
(Korean Abstract)
Áö´ÉÇü À½¼º ´ëÈ­ ÀÎÅÍÆäÀ̽º ±¸Çö¿¡ ÀÖ¾î ÇٽɾîÀÇ ÀǹÌÇ¥Áö´Â »ç¿ëÀÚ Àǵµ ÆľÇÀ» À§ÇÑ Áß¿äÇÑ ¿ä¼ÒÀÌ´Ù. ´ëÈ­½Ã½ºÅÛÀº »ç¿ëÀÚ ¹ßÈ­ÀÇ Àǵµ¸¦ ÆľÇÇϱâ À§ÇØ Çٽɾî¿Í ±× ÀǹÌÇ¥Áö¸¦ ÀÌ¿ëÇÏ¿© ¹ßÈ­ÀÇ Àǵµ¸¦ °áÁ¤ÇÑ´Ù. ÇϳªÀÇ Çٽɾî´Â ¿©·¯ °³ÀÇ ÀǹÌÇ¥Áö¸¦ °¡Áú ¼ö ÀÖ´Â ÁßÀǼºÀ» Áö´Ñ´Ù. ÀÌ·¯ÇÑ ÁßÀǼºÀ» Áö´Ñ Çٽɾ »ç¿ëÀÚÀÇ Àǵµ¿Í ÀÏÄ¡ÇÏ´Â ÀǹÌÇ¥Áö·Î °áÁ¤ÇÏ´Â °ÍÀº ´Ü¾î ÀÇ¹Ì ºÐº° ¹®Á¦¿Í À¯»çÇÏ´Ù. ¿ì¸®´Â Àü»çµÈ ´ëÈ­ ¸»¹¶Ä¡ÀÇ ¾à 23%¸¦ ¼öµ¿À¸·Î Àǹ̸¦ ºÎÂøÇÏ¿© Çٽɾ ´ëÇÑ ÀǹÌÇ¥Áö »çÀü, À¯ÀÇ¾î »çÀü, ¹®¸Æº¤ÅÍ »çÀüÀ» ¸ÕÀú ±¸ÃàÇÑ ÈÄ, ³ª¸ÓÁö 77%´ëÈ­ ¸»¹¶Ä¡¿¡ Á¸ÀçÇÏ´Â ÇٽɾîÀÇ Àǹ̸¦ ÀÚµ¿À¸·Î ºÎÂøÇÑ´Ù. ÁßÀǼºÀ» °¡Áø Çٽɾî´Â ¹®¸Æº¤ÅÍ »çÀüÀ¸·ÎºÎÅÍ ¹®¸Æ º¤ÅÍ À¯»çµµ¸¦ °è»êÇÏ¿© Àǹ̸¦ °áÁ¤ÇÑ´Ù. Çٽɾ ¹Ìµî·Ï¾îÀÎ °æ¿ì¿¡´Â À¯ÀÇ¾î »çÀüÀ» ÀÌ¿ëÇÏ¿© °¡Àå À¯»çÇÑ Çٽɾ ã¾Æ ±× ÇٽɾîÀÇ Àǹ̸¦ ºÎÂøÇÑ´Ù. ÁßÀǼºÀ» °¡Áø °íºóµµ Çٽɾî 3°³¿Í Àúºóµµ Çٽɾî 3°³¸¦ ¸»¹¶Ä¡¿¡¼­ ¼±Á¤ÇÏ¿© Á¦¾È ½Ã½ºÅÛÀÇ ¼º´ÉÀ» Æò°¡ÇÏ¿´´Ù. ½ÇÇè°á°ú, ¼öµ¿À¸·Î ±¸ÃàÇÑ ¸»¹¶Ä¡¸¦ »ç¿ëÇÏ¿´À» ¶§ ¾à 54.4%ÀÇ Á¤È®µµ¸¦ ¾ò¾ú°í, ¹ÝÀÚµ¿À¸·Î È®ÀåÇÑ ¸»¹¶Ä¡¸¦ »ç¿ëÇÏ¿´À» ¶§ ¾à 50.0%ÀÇ Á¤È®µµ¸¦ ¾ò¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Determining the meaning of a keyword in a speech dialogue system is an important technology for the future implementation of an intelligent speech dialogue interface. After extracting keywords to grasp intention from user's utterance, the intention of utterance is determined by using the semantic mark of keyword. One keyword can have several semantic marks, and we regard the task of attaching the correct semantic mark to the user¡¯s intentions on these keyword as a problem of word sense disambiguation. In this study, about 23% of all keywords in the corpus is manually tagged to build a semantic mark dictionary, a synonym dictionary, and a context vector dictionary, and then the remaining 77% of all keywords is automatically tagged. The semantic mark of a keyword is determined by calculating the context vector similarity from the context vector dictionary. For an unregistered keyword, the semantic mark of the most similar keyword is attached using a synonym dictionary. We compare the performance of the system with manually constructed training set and semi-automatically expanded training set by selecting 3 high-frequency keywords and 3 low-frequency keywords in the corpus. In experiments, we obtained accuracy of 54.4% with manually constructed training set and 50.0% with semi-automatically expanded training set.
Å°¿öµå(Keyword) ´ëÈ­ ¸»¹¶Ä¡   ÀÇ¹Ì Ç¥Áö ű렠 ¹®¸Æ º¤ÅÍ À¯»çµµ   Dialogue Corpus   Semantic Mark Tagging   Context Vector Similarity   ´ëÈ­ ¸»¹¶Ä¡   ÀÇ¹Ì Ç¥Áö ű렠 ¹®¸Æ º¤ÅÍ À¯»çµµ   Dialogue Corpus   Semantic Mark Tagging   Context Vector Similarity  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå